© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16366
    Prev
    Next
    INDEX
    Explanations

    specific references to government entities or political branches

    oai_token-act-pair · gpt-3.5-turbo

    references to government and legal institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenant
    -0.75
    ģ
    -0.72
    ometimes
    -0.71
    ¿½
    -0.69
    hots
    -0.67
    hops
    -0.67
    warts
    -0.65
    µ
    -0.64
    ī
    -0.63
    Ĵ
    -0.63
    POSITIVE LOGITS
    's
    1.34
    ÃŃs
    1.04
    \'
    0.92
    ´
    0.86
    wide
    0.84
     motto
    0.77
     playbook
    0.77
    �
    0.76
     mandate
    0.75
     lockout
    0.75
    Activations Density 0.318%

    No Known Activations